Coupled network for robust pedestrian detection with gated multi-layer feature extraction and deformable occlusion handling
Pedestrian detection methods have been significantly improved with the development of
deep convolutional neural networks. Nevertheless, detecting ismall-scaled pedestrians and …
deep convolutional neural networks. Nevertheless, detecting ismall-scaled pedestrians and …
Adapted center and scale prediction: more stable and more accurate
W Wang - arXiv preprint arXiv:2002.09053, 2020 - arxiv.org
Pedestrian detection benefits from deep learning technology and gains rapid development
in recent years. Most of detectors follow general object detection frame, ie default boxes and …
in recent years. Most of detectors follow general object detection frame, ie default boxes and …
A new multi-scale pedestrian detection algorithm in traffic environment
J Ren, J Han - Journal of Electrical Engineering & Technology, 2021 - Springer
Pedestrian detection in traffic environment requires high accuracy and speed of the
algorithm. Traditional methods can meet the speed requirement, but there is a long gap in …
algorithm. Traditional methods can meet the speed requirement, but there is a long gap in …
Context-aware pedestrian detection especially for small-sized instances with Deconvolution Integrated Faster RCNN (DIF R-CNN)
H Xie, Y Chen, H Shin - Applied Intelligence, 2019 - Springer
Pedestrian detection is a canonical problem in computer vision. Motivated by the
observation that the major bottleneck of pedestrian detection lies on the different scales of …
observation that the major bottleneck of pedestrian detection lies on the different scales of …
Pedhunter: Occlusion robust pedestrian detector in crowded scenes
Pedestrian detection in crowded scenes is a challenging problem, because occlusion
happens frequently among different pedestrians. In this paper, we propose an effective and …
happens frequently among different pedestrians. In this paper, we propose an effective and …
A parallel vision approach to scene-specific pedestrian detection
In recent years, with the development of computing power and deep learning algorithms,
pedestrian detection has made great progress. Nevertheless, once a detection model …
pedestrian detection has made great progress. Nevertheless, once a detection model …
PCN: Part and context information for pedestrian detection with CNNs
Pedestrian detection has achieved great improvements in recent years, while complex
occlusion handling is still one of the most important problems. To take advantage of the body …
occlusion handling is still one of the most important problems. To take advantage of the body …
Improved center and scale prediction-based pedestrian detection using convolutional block
Pedestrian detection is an important computer vision algorithm in advanced driver
assistance systems (ADAS). In this paper, we propose a deep learning-based pedestrian …
assistance systems (ADAS). In this paper, we propose a deep learning-based pedestrian …
Asymmetric multi-stage CNNs for small-scale pedestrian detection
A critical bottleneck in pedestrian detection is the detection of small-scale pedestrians, which
have low contrast and blurry shapes in images and videos. Considered that the body shape …
have low contrast and blurry shapes in images and videos. Considered that the body shape …
Pedestrian detection algorithm based on improved faster rcnn
X Shao, J Wei, D Guo, R Zheng, X Nie… - 2021 IEEE 5th …, 2021 - ieeexplore.ieee.org
To solve the problem of poor detection effect of small-scale pedestrian in the image, based
on the existing deep convolutional neural network (CNN) model. We propose an improved …
on the existing deep convolutional neural network (CNN) model. We propose an improved …